Renamed webqtlDataSet.py to data_set.py

Renamed the class webqtlDataset to DataSet

Finished cisLRS and transLRS search types in d_search.py

Fixed parent/f1 issue in show_trait.py

4 files changed, 99 insertions, 106 deletions

diff --git a/wqflask/base/webqtlDataset.py b/wqflask/base/data_set.py
index 933077fd..992c673e 100755
--- a/wqflask/base/webqtlDataset.py
+++ b/wqflask/base/data_set.py
@@ -30,7 +30,7 @@ import webqtlConfig
 
 
 
-class webqtlDataset:
+class DataSet(object):
     """
     Dataset class defines a dataset in webqtl, can be either Microarray,
     Published phenotype, genotype, or user input dataset(temp)
@@ -55,14 +55,7 @@ class webqtlDataset:
             self.fullname = 'Temporary Storage'
             self.shortname = 'Temp'
         elif dbName.find('Publish') >= 0:
-            self.searchfield = ['name','post_publication_description','abstract','title','authors']
-            self.disfield = ['name','pubmed_id',
-                            'pre_publication_description', 'post_publication_description', 'original_description',
-                            'pre_publication_abbreviation', 'post_publication_abbreviation',
-                            'lab_code', 'submitter', 'owner', 'authorized_users',
-                            'authors','title','abstract', 'journal','volume','pages','month',
-                            'year','sequence', 'units', 'comments']
-            self.type = 'Publish'
+            pass
         elif dbName.find('Geno') >= 0:
             self.searchfield = ['name','chr']
             self.disfield = ['name','chr','mb', 'source2', 'sequence']
@@ -155,3 +148,15 @@ class webqtlDataset:
     def genHTML(self, Class='c0dd'):
         return  HT.Href(text = HT.Span('%s Database' % self.fullname, Class= "fwb " + Class),
                 url= webqtlConfig.INFOPAGEHREF % self.name,target="_blank")
+
+class PhenotypeDataSet(DataSet):
+    
+    def __init__(self):
+        self.searchfield = ['name','post_publication_description','abstract','title','authors']
+        self.disfield = ['name','pubmed_id',
+                            'pre_publication_description', 'post_publication_description', 'original_description',
+                            'pre_publication_abbreviation', 'post_publication_abbreviation',
+                            'lab_code', 'submitter', 'owner', 'authorized_users',
+                            'authors','title','abstract', 'journal','volume','pages','month',
+                            'year','sequence', 'units', 'comments']
+        self.type = 'Publish'
\ No newline at end of file
diff --git a/wqflask/wqflask/do_search.py b/wqflask/wqflask/do_search.py
index fd03f359..e2bafb3a 100644
--- a/wqflask/wqflask/do_search.py
+++ b/wqflask/wqflask/do_search.py
@@ -49,65 +49,6 @@ class DoSearch(object):
         return cls.search_types[search_type]
 
 
-class ProbeSetSearch(DoSearch):
-    """A search within an mRNA expression dataset"""
-
-    DoSearch.search_types['ProbeSet'] = "ProbeSetSearch"
-
-    base_query = """SELECT ProbeSet.Name as TNAME,
-                0 as thistable,
-                ProbeSetXRef.Mean as TMEAN,
-                ProbeSetXRef.LRS as TLRS,
-                ProbeSetXRef.PVALUE as TPVALUE,
-                ProbeSet.Chr_num as TCHR_NUM,
-                ProbeSet.Mb as TMB,
-                ProbeSet.Symbol as TSYMBOL,
-                ProbeSet.name_num as TNAME_NUM
-                FROM ProbeSetXRef, ProbeSet """
-
-
-    def compile_final_query(self, from_clause = '', where_clause = ''):
-        """Generates the final query string"""
-        
-        from_clause = ''
-        from_clause = self.normalize_spaces(from_clause)
-
-        query = (self.base_query +
-            """%s
-                WHERE %s
-                    and ProbeSet.Id = ProbeSetXRef.ProbeSetId
-                    and ProbeSetXRef.ProbeSetFreezeId = %s
-                            """ % (self.escape(from_clause),
-                                    where_clause,
-                                    self.escape(self.dataset.id)))        
-
-        print("query is:", pf(query))
-
-        return query
-
-    def run(self):
-        """Generates and runs a simple search of an mRNA expression dataset"""
-
-        print("Running ProbeSetSearch")
-        query = (self.base_query +
-                """WHERE (MATCH (ProbeSet.Name,
-                    ProbeSet.description,
-                    ProbeSet.symbol,
-                    alias,
-                    GenbankId,
-                    UniGeneId,
-                    Probe_Target_Description)
-                    AGAINST ('%s' IN BOOLEAN MODE)) 
-                    and ProbeSet.Id = ProbeSetXRef.ProbeSetId
-                    and ProbeSetXRef.ProbeSetFreezeId = %s  
-                            """ % (self.escape(self.search_term),
-                            self.escape(self.dataset.id)))
-
-        print("final query is:", pf(query))
-
-        return self.execute(query)
-
-
 class PhenotypeSearch(DoSearch):
     """A search within a phenotype dataset"""
 
@@ -212,6 +153,65 @@ class GenotypeSearch(DoSearch):
 
         return self.execute(query)
 
+
+class ProbeSetSearch(DoSearch):
+    """A search within an mRNA expression dataset"""
+
+    DoSearch.search_types['ProbeSet'] = "ProbeSetSearch"
+
+    base_query = """SELECT ProbeSet.Name as TNAME,
+                0 as thistable,
+                ProbeSetXRef.Mean as TMEAN,
+                ProbeSetXRef.LRS as TLRS,
+                ProbeSetXRef.PVALUE as TPVALUE,
+                ProbeSet.Chr_num as TCHR_NUM,
+                ProbeSet.Mb as TMB,
+                ProbeSet.Symbol as TSYMBOL,
+                ProbeSet.name_num as TNAME_NUM
+                FROM ProbeSetXRef, ProbeSet """
+
+
+    def compile_final_query(self, from_clause, where_clause):
+        """Generates the final query string"""
+
+        from_clause = self.normalize_spaces(from_clause)
+
+        query = (self.normalize_spaces(self.base_query) +
+            """%s
+                WHERE %s
+                    and ProbeSet.Id = ProbeSetXRef.ProbeSetId
+                    and ProbeSetXRef.ProbeSetFreezeId = %s
+                            """ % (self.escape(from_clause),
+                                    where_clause,
+                                    self.escape(self.dataset.id)))        
+
+        print("query is:", pf(query))
+
+        return query
+
+    def run(self):
+        """Generates and runs a simple search of an mRNA expression dataset"""
+
+        print("Running ProbeSetSearch")
+        query = (self.base_query +
+                """WHERE (MATCH (ProbeSet.Name,
+                    ProbeSet.description,
+                    ProbeSet.symbol,
+                    alias,
+                    GenbankId,
+                    UniGeneId,
+                    Probe_Target_Description)
+                    AGAINST ('%s' IN BOOLEAN MODE)) 
+                    and ProbeSet.Id = ProbeSetXRef.ProbeSetId
+                    and ProbeSetXRef.ProbeSetFreezeId = %s  
+                            """ % (self.escape(self.search_term),
+                            self.escape(self.dataset.id)))
+
+        print("final query is:", pf(query))
+
+        return self.execute(query)
+    
+
 class RifSearch(ProbeSetSearch):
     """Searches for traits with a Gene RIF entry including the search term."""
 
@@ -283,7 +283,7 @@ class LrsSearch(ProbeSetSearch):
 
     DoSearch.search_types['LRS'] = 'LrsSearch'
     
-class CisLrsSearch(LrsSearch):
+class CisLrsSearch(ProbeSetSearch):
     """Searches for genes on a particular chromosome with a cis-eQTL within the given LRS values
 
     A cisLRS search can take 2 forms:
@@ -305,9 +305,12 @@ class CisLrsSearch(LrsSearch):
     DoSearch.search_types['CISLRS'] = "CisLrsSearch"
 
     def run(self):
+        
+        from_clause = ", Geno "
+        
         if len(self.search_term) == 3:
             lower_limit, upper_limit, min_threshold = [int(value) for value in self.search_term]
-            
+
             where_clause = """ %sXRef.LRS > %s and
                 %sXRef.LRS < %s  and
                 %sXRef.Locus = Geno.name and
@@ -327,7 +330,7 @@ class CisLrsSearch(LrsSearch):
         else:
             NeedSomeErrorHere     
 
-        query = self.compile_final_query(where_clause)
+        query = self.compile_final_query(from_clause, where_clause)
 
         return self.execute(query)
     
@@ -353,6 +356,8 @@ class TransLrsSearch(LrsSearch):
     DoSearch.search_types['TRANSLRS'] = "TransLrsSearch"
 
     def run(self):
+        from_clause = ", Geno "
+        
         if len(self.search_term) == 3:
             lower_limit, upper_limit, min_threshold = [int(value) for value in self.search_term]
             
@@ -374,9 +379,11 @@ class TransLrsSearch(LrsSearch):
                     )
 
         else:
-            NeedSomeErrorHere            
+            NeedSomeErrorHere     
 
-        return None
+        query = self.compile_final_query(from_clause, where_clause)
+
+        return self.execute(query)
 
 
 #itemCmd = item[0]
@@ -447,7 +454,7 @@ if __name__ == "__main__":
     #results = ProbeSetSearch("salt", dataset, cursor, db_conn).run()
     #results = RifSearch("diabetes", dataset, cursor, db_conn).run()
     #results = WikiSearch("nicotine", dataset, cursor, db_conn).run()
-    results = CisLrsSearch(['9','99','10'], dataset, cursor, db_conn).run()
+    results = TransLrsSearch(['25','99','10'], dataset, cursor, db_conn).run()
     #results = TransLrsSearch(['9', '999', '10'], dataset, cursor, db_conn).run()
     #results = PhenotypeSearch("brain", dataset, cursor, db_conn).run()
     #results = GenotypeSearch("rs13475699", dataset, cursor, db_conn).run()
diff --git a/wqflask/wqflask/search_results.py b/wqflask/wqflask/search_results.py
index dc3c72fc..05f062fc 100644
--- a/wqflask/wqflask/search_results.py
+++ b/wqflask/wqflask/search_results.py
@@ -84,16 +84,7 @@ class SearchResultPage(templatePage):
             print("self.dataset is:", pf(self.dataset))
             self.dataset = webqtlDataset(self.dataset, self.cursor)
             print("self.dataset is now:", pf(self.dataset))
-            #self.dataset = map(lambda x: webqtlDataset(x, self.cursor), self.dataset)
-            #currently, webqtl won't allow multiple crosses
-            #for other than multiple publish db search
-            #so we can use the first dataset as example
-            #if self.dataset.type=="Publish":
-            #    pass
             if self.dataset.type in ("Geno", "ProbeSet"):
-
-                #userExist = None
-                # Can't use paramater substitution for table names apparently
                 db_type = self.dataset.type + "Freeze"
                 print("db_type [%s]: %s" % (type(db_type), db_type))
 
@@ -124,11 +115,8 @@ class SearchResultPage(templatePage):
                     #        access_to_confidential_dataset = 1
                     #
                     #if not access_to_confidential_dataset:
-                    #    #Error, No dataset selected
-                    #    heading = "Search Result"
-                    #    detail = ["The %s dataset you selected is not open to the public at this time, please go back and SELECT other dataset." % indFullName]
-                    #    self.error(heading=heading,detail=detail,error="Confidential dataset")
-                    #    return
+                    #    Some error
+
             #else:
             #    heading = "Search Result"
             #    detail = ['''The dataset has not been established yet, please
@@ -180,7 +168,8 @@ class SearchResultPage(templatePage):
                                 'Max LRS',
                                 'Max LRS Location']
         elif self.dataset.type == "Geno":
-            self.search_fields = ['Name','Chr']
+            self.search_fields = ['Name',
+                                  'Chr']
             self.header_fields = ['',
                                 'ID',
                                 'Location']
@@ -241,7 +230,6 @@ class SearchResultPage(templatePage):
             # This is throwing an error when a_search['key'] is None, so I changed above    
             #search_type = string.upper(a_search['key'])
             #if not search_type:
-            #    # We fall back to the dataset type as the key to get the right object
             #    search_type = self.dataset.type
 
             search_ob = do_search.DoSearch.get_search(search_type)
@@ -273,7 +261,6 @@ class SearchResultPage(templatePage):
     
 
     def getTraitInfoForGeno(self, trait_list):
-
         for this_trait in trait_list:
             if not this_trait.haveinfo:
                 this_trait.retrieveInfo()
@@ -295,8 +282,7 @@ class SearchResultPage(templatePage):
                 this_trait.location_value = trait_location_value
 
 
-    def getTraitInfoForPublish(self, trait_list, species=''):
-
+    def getTraitInfoForPublish(self, trait_list, species = ''):
         for this_trait in trait_list:
             if not this_trait.haveinfo:
                 this_trait.retrieveInfo(QTL=1)
@@ -307,18 +293,16 @@ class SearchResultPage(templatePage):
                     description = this_trait.pre_publication_description
             this_trait.description_display = description
 
-            try:
-                this_trait.pubmed_text =  int(this_trait.year)
-            except:
+            if not this_trait.year.isdigit():
                 this_trait.pubmed_text = "N/A"
 
             if this_trait.pubmed_id:
                 this_trait.pubmed_link = webqtlConfig.PUBMEDLINK_URL % this_trait.pubmed_id
 
             #LRS and its location
-            this_trait.LRS_score_repr = 'N/A'
+            this_trait.LRS_score_repr = "N/A"
             this_trait.LRS_score_value = 0
-            this_trait.LRS_location_repr = 'N/A'
+            this_trait.LRS_location_repr = "N/A"
             this_trait.LRS_location_value = 1000000
 
             if this_trait.lrs:
@@ -408,7 +392,7 @@ class SearchResultPage(templatePage):
     ProbeSet.Name = '%s'
             """ % (self.db_conn.escape_string(str(this_trait.db.id)),
                    self.db_conn.escape_string(this_trait.name)))
-            
+
             print("query is:", pf(query))
             
             self.cursor.execute(query)
diff --git a/wqflask/wqflask/show_trait/show_trait.py b/wqflask/wqflask/show_trait/show_trait.py
index 19e67c43..3dac5933 100755
--- a/wqflask/wqflask/show_trait/show_trait.py
+++ b/wqflask/wqflask/show_trait/show_trait.py
@@ -1509,10 +1509,10 @@ class ShowTrait(templatePage):
 
 
     def make_sample_lists(self, fd, variance_data_page, this_trait):
-        if fd.genotype.type == "riset":
-            all_samples_ordered = fd.f1list + fd.samplelist
-        else:
+        if fd.parlist:
             all_samples_ordered = fd.parlist + fd.f1list + fd.samplelist
+        else:
+            all_samples_ordered = fd.f1list + fd.samplelist
 
         this_trait_samples = set(this_trait.data.keys())
 
@@ -1527,8 +1527,6 @@ class ShowTrait(templatePage):
                                         this_trait=this_trait,
                                         sample_group_type='primary',
                                         header="%s Only" % (fd.RISet))
-        
-        print("primary_samples.attributes:", pf(primary_samples.attributes))
 
         other_sample_names = []
         for sample in this_trait.data.keys():
@@ -1538,8 +1536,7 @@ class ShowTrait(templatePage):
                 other_sample_names.append(sample)
 
         if other_sample_names:
-            unappended_par_f1 = fd.f1list + fd.parlist
-            par_f1_samples = ["_2nd_" + sample for sample in unappended_par_f1]
+            par_f1_samples = fd.parlist + fd.f1list
             
             other_sample_names.sort() #Sort other samples
             other_sample_names = par_f1_samples + other_sample_names